Reliable and Responsible Foundation Models: A Comprehensive Survey
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914314857742336 |
|---|---|
| author | Yang, Xinyu Han, Junlin Bommasani, Rishi Luo, Jinqi Qu, Wenjie Zhou, Wangchunshu Bibi, Adel Wang, Xiyao Yoon, Jaehong Stengel-Eskin, Elias Tong, Shengbang Shen, Lingfeng Rafailov, Rafael Li, Runjia Wang, Zhaoyang Zhou, Yiyang Cui, Chenhang Wang, Yu Zheng, Wenhao Zhou, Huichi Gu, Jindong Chen, Zhaorun Xia, Peng Lee, Tony Zollo, Thomas Sehwag, Vikash Leng, Jixuan Chen, Jiuhai Wen, Yuxin Zhang, Huan Deng, Zhun Zhang, Linjun Izmailov, Pavel Koh, Pang Wei Tsvetkov, Yulia Wilson, Andrew Zhang, Jiaheng Zou, James Xie, Cihang Wang, Hao Torr, Philip McAuley, Julian Alvarez-Melis, David Tramèr, Florian Xu, Kaidi Jana, Suman Callison-Burch, Chris Vidal, Rene Kokkinos, Filippos Bansal, Mohit Chen, Beidi Yao, Huaxiu |
| author_facet | Yang, Xinyu Han, Junlin Bommasani, Rishi Luo, Jinqi Qu, Wenjie Zhou, Wangchunshu Bibi, Adel Wang, Xiyao Yoon, Jaehong Stengel-Eskin, Elias Tong, Shengbang Shen, Lingfeng Rafailov, Rafael Li, Runjia Wang, Zhaoyang Zhou, Yiyang Cui, Chenhang Wang, Yu Zheng, Wenhao Zhou, Huichi Gu, Jindong Chen, Zhaorun Xia, Peng Lee, Tony Zollo, Thomas Sehwag, Vikash Leng, Jixuan Chen, Jiuhai Wen, Yuxin Zhang, Huan Deng, Zhun Zhang, Linjun Izmailov, Pavel Koh, Pang Wei Tsvetkov, Yulia Wilson, Andrew Zhang, Jiaheng Zou, James Xie, Cihang Wang, Hao Torr, Philip McAuley, Julian Alvarez-Melis, David Tramèr, Florian Xu, Kaidi Jana, Suman Callison-Burch, Chris Vidal, Rene Kokkinos, Filippos Bansal, Mohit Chen, Beidi Yao, Huaxiu |
| contents | Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, science, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08145 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reliable and Responsible Foundation Models: A Comprehensive Survey Yang, Xinyu Han, Junlin Bommasani, Rishi Luo, Jinqi Qu, Wenjie Zhou, Wangchunshu Bibi, Adel Wang, Xiyao Yoon, Jaehong Stengel-Eskin, Elias Tong, Shengbang Shen, Lingfeng Rafailov, Rafael Li, Runjia Wang, Zhaoyang Zhou, Yiyang Cui, Chenhang Wang, Yu Zheng, Wenhao Zhou, Huichi Gu, Jindong Chen, Zhaorun Xia, Peng Lee, Tony Zollo, Thomas Sehwag, Vikash Leng, Jixuan Chen, Jiuhai Wen, Yuxin Zhang, Huan Deng, Zhun Zhang, Linjun Izmailov, Pavel Koh, Pang Wei Tsvetkov, Yulia Wilson, Andrew Zhang, Jiaheng Zou, James Xie, Cihang Wang, Hao Torr, Philip McAuley, Julian Alvarez-Melis, David Tramèr, Florian Xu, Kaidi Jana, Suman Callison-Burch, Chris Vidal, Rene Kokkinos, Filippos Bansal, Mohit Chen, Beidi Yao, Huaxiu Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Computers and Society Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, science, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible. |
| title | Reliable and Responsible Foundation Models: A Comprehensive Survey |
| topic | Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Computers and Society |
| url | https://arxiv.org/abs/2602.08145 |